Data Requirements for Applying Machine Learning to Energy Disaggregation

Abstract

Energy disaggregation, or nonintrusive load monitoring (NILM), is a technology for separating a household’s aggregate electricity consumption information. Although this technology was developed in 1992, its practical usage and mass deployment have been rather limited, possibly because the commonly used datasets are not adequate for NILM research. In this study, we report the findings from a newly collected dataset that contains 10 Hz sampling data for 58 houses. The dataset not only contains the aggregate measurements, but also individual appliance measurements for three types of appliances. By applying three classification algorithms (vanilla DNN (Deep Neural Network), ML (Machine Learning) with feature engineering, and CNN (Convolutional Neural Network) with hyper-parameter tuning) and a recent regression algorithm (Subtask Gated Network) to the new dataset, we show that NILM performance can be significantly limited when the data sampling rate is too low or when the number of distinct houses in the dataset is too small. The well-known NILM datasets that are popular in the research community do not meet these requirements. Our results indicate that higher quality datasets should be used to expedite the progress of NILM research.

The ENERTALK dataset, 15 Hz electricity consumption data from 22 houses in Korea

“…Shin et al . also reported that higher sampling rates can be beneficial for empirical energy disaggregation because the appliance signatures become more visible as the sampling rate increases 53 . In line with these studies, Fig.…”

Review on Deep Neural Networks Applied to Low-Frequency NILM

“…While the range of sampling frequencies in the reviewed literature extends from 1 3600 Hz [60,61] to 10 Hz [62], the large majority of the reviewed works employ either 1 60 Hz or values between 1 and 1 10 Hz. It is noteworthy that in two cases data were upsampled to have a higher frequency than the original dataset [63,64].…”

“…It is noteworthy that in two cases data were upsampled to have a higher frequency than the original dataset [63,64]. Results on the influence of the sampling frequency on disaggregation results are presented in different studies [62,[65][66][67]. Most of these studies find a marked dependence on the device [62,65,66].…”

“…Results on the influence of the sampling frequency on disaggregation results are presented in different studies [62,[65][66][67]. Most of these studies find a marked dependence on the device [62,65,66]. This can be attributed to certain devices exhibiting more frequent fluctuations that get lost at lower resolution.…”

“…This can be attributed to certain devices exhibiting more frequent fluctuations that get lost at lower resolution. [62] analyzes sampling rates from 10 Hz down to 0.03 Hz for on/off classification and energy estimation for TV, washing machine, rice cooker. They find that to prevent performance loss for the classification and regression tasks, the sampling rates should be at least 1 Hz and 3 Hz, respectively.…”